https://github.com/rcmalli/keras-squeezenet

SqueezeNet implementation with Keras Framework
https://github.com/rcmalli/keras-squeezenet

deeplearning keras squeezenet tensorflow

Last synced: 3 days ago
JSON representation

SqueezeNet implementation with Keras Framework

• Host: GitHub
• URL: https://github.com/rcmalli/keras-squeezenet
• Owner: rcmalli
• License: mit
• Created: 2016-10-08T12:29:26.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2023-02-24T15:38:04.000Z (almost 2 years ago)
• Last Synced: 2024-11-29T05:29:15.792Z (14 days ago)
• Topics: deeplearning, keras, squeezenet, tensorflow
• Language: Python
• Homepage:
• Size: 10.4 MB
• Stars: 404
• Watchers: 18
• Forks: 146
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-image-classification - unofficial-keras : https://github.com/rcmalli/keras-squeezenet
• awesome-image-classification - unofficial-keras : https://github.com/rcmalli/keras-squeezenet

README

        
# keras-squeezenet [![Build Status](https://travis-ci.org/rcmalli/keras-squeezenet.svg?branch=master)](https://travis-ci.org/rcmalli/keras-squeezenet)

SqueezeNet v1.1 Implementation using Keras Functional Framework 2.0

This [network model](https://github.com/rcmalli/keras-squeezenet/blob/master/images/SqueezeNet.png) has AlexNet accuracy with small footprint (5.1 MB)

Pretrained models are converted from original Caffe network.

~~~bash

# Most Recent One

pip install git+https://github.com/rcmalli/keras-squeezenet.git

# Release Version

pip install keras_squeezenet

~~~

### News

- Project is now up-to-date with the new Keras version (2.0).

- Old Implementation is still available at 'keras1' branch but not updated.

### Library Versions

- Keras v2.1.1

- Tensorflow v1.4

### Example Usage

~~~python

import numpy as np

from keras_squeezenet import SqueezeNet

from keras.applications.imagenet_utils import preprocess_input, decode_predictions

from keras.preprocessing import image

model = SqueezeNet()

img = image.load_img('../images/cat.jpeg', target_size=(227, 227))

x = image.img_to_array(img)

x = np.expand_dims(x, axis=0)

x = preprocess_input(x)

preds = model.predict(x)

print('Predicted:', decode_predictions(preds))

~~~

### References

1) [Keras Framework](www.keras.io)

2) [SqueezeNet Official Github Repo](https://github.com/DeepScale/SqueezeNet)

3) [SqueezeNet Paper](http://arxiv.org/abs/1602.07360)

### Licence 

MIT License 

Note: If you find this project useful, please include reference link in your work.